Downloads · 30 days
32
7% of all-time downloads
RichardErkhov/KaeriJenti_-_kaori-34b-v3-gguf
KaeriJenti_-_kaori-34b-v3-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
32
7% of all-time downloads
All-time downloads
442
Public
Repo size
389 GB
Likes
0
Public
Click a slice to open those files.
.gguf451 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
kaori-34b-v3 - GGUF
| Name | Quant method | Size |
|---|---|---|
| kaori-34b-v3.Q2_K.gguf | Q2_K | 11.94GB |
| kaori-34b-v3.IQ3_XS.gguf | IQ3_XS | 13.26GB |
| kaori-34b-v3.IQ3_S.gguf | IQ3_S | 13.99GB |
| kaori-34b-v3.Q3_K_S.gguf | Q3_K_S | 13.93GB |
| kaori-34b-v3.IQ3_M.gguf | IQ3_M | 14.5GB |
| kaori-34b-v3.Q3_K.gguf | Q3_K | 15.51GB |
| kaori-34b-v3.Q3_K_M.gguf | Q3_K_M | 15.51GB |
| kaori-34b-v3.Q3_K_L.gguf | Q3_K_L | 16.89GB |
| kaori-34b-v3.IQ4_XS.gguf | IQ4_XS | 17.36GB |
| kaori-34b-v3.Q4_0.gguf | Q4_0 | 18.13GB |
| kaori-34b-v3.IQ4_NL.gguf | IQ4_NL | 18.3GB |
| kaori-34b-v3.Q4_K_S.gguf | Q4_K_S | 18.25GB |
| kaori-34b-v3.Q4_K.gguf | Q4_K | 19.24GB |
| kaori-34b-v3.Q4_K_M.gguf | Q4_K_M | 19.24GB |
| kaori-34b-v3.Q4_1.gguf | Q4_1 | 20.1GB |
| kaori-34b-v3.Q5_0.gguf | Q5_0 | 22.08GB |
| kaori-34b-v3.Q5_K_S.gguf | Q5_K_S | 22.08GB |
| kaori-34b-v3.Q5_K.gguf | Q5_K | 22.65GB |
| kaori-34b-v3.Q5_K_M.gguf | Q5_K_M | 22.65GB |
| kaori-34b-v3.Q5_1.gguf | Q5_1 | 24.05GB |
| kaori-34b-v3.Q6_K.gguf | Q6_K | 26.28GB |
| kaori-34b-v3.Q8_0.gguf | Q8_0 | 34.03GB |
This Model was Finetuned By Kaeri and Jenti.
<h3>Datasets Strategy</h3>We trained the model with 100% Open-Platypus data and 5% Dolphin data and applied SFT strategy.
We did not use GSM8k samples when generating data. Also we were careful of data contamination by similarity filtering the training data if the data correspond to any of the following list.
<pre> filtering_tasks = [ 'cot_gsm8k', 'cot_gsm8k_ii', 'drop:2.0.0', 'winogrande:1.1.0' 'task228_arc_answer_generation_easy', 'ai2_arc/ARC-Challenge:1.0.0', 'ai2_arc/ARC-Easy:1.0.0', 'task229_arc_answer_generation_hard', 'hellaswag:1.1.0', 'task1389_hellaswag_completion' ] </pre> <h3>Framework:</h3> <h3>Parameters:</h3>